wan-2-7

Name: wan-2-7
Author: prime-skills

31stars9forks

How to install wan-2-7?

prime-skills/runcomfy-agent-skills/wan-2-7

$npx -y skills add prime-skills/runcomfy-agent-skills --skill wan-2-7

Installs into the current project.

Summary

Generate text-to-video with Wan 2.7 (Wan-AI's flagship motion model) on RunComfy. Documents Wan 2.7's strengths (multi-reference conditioning, audio-driven lip-sync via audio_url, smoother transitions, prompt expansion), the duration / resolution / aspect-ratio schema, and when

Files · 1

View on GitHub

SKILL.md

1	# Wan 2.7 — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=wan-2-7) · [Text-to-video](https://www.runcomfy.com/models/wan-ai/wan-2-7/text-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=wan-2-7) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/wan-2-7)
4
5	Wan-AI's Wan 2.7 — flagship video model with multi-reference conditioning and audio-driven lip-sync — hosted on the RunComfy Model API.
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill wan-2-7 -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	\| You want \| Use \|
14	\|---\|---\|
15	\| Lip-sync video to an audio track you supply \| Wan 2.7 (`audio_url`) \|
16	\| Multi-reference fine motion control \| Wan 2.7 \|
17	\| Smooth transitions, accurate motion physics \| Wan 2.7 \|
18	\| Currently-#1 blind-vote video model \| HappyHorse 1.0 \|
19	\| Multi-modal cinematic with image+video+audio refs + in-pass voice generation \| Seedance 2.0 Pro \|
20	\| Cinematic motion editing on existing footage \| Kling Video O1 \|
21	\| Ultra-fast iteration \| LTX 2 \|
22
23	If the user said "Wan" / "Wan 2.7" / "wan-ai" / "alibaba video" explicitly, route here regardless.
24
25	## Prerequisites
26
27	1. RunComfy CLI — `npm i -g @runcomfy/cli`
28	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
29	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
30
31	## Endpoints + input schema
32
33	### `wan-ai/wan-2-7/text-to-video`
34
35	\| Field \| Type \| Required \| Default \| Notes \|
36	\|---\|---\|---\|---\|---\|
37	\| `prompt` \| string \| yes \| — \| Up to ~5000 chars / ~1500 tokens. \|
38	\| `audio_url` \| string \| no \| — \| WAV/MP3, 3–30s, ≤15MB. Drives lip-sync. Omit → background music auto-generated. \|
39	\| `aspect_ratio` \| enum \| no \| `16:9` \| `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. \|
40	\| `resolution` \| enum \| no \| `1080p` \| `720p` or `1080p`. \|
41	\| `duration` \| enum \| no \| `5` \| 2–15 (whole seconds). \|
42	\| `negative_prompt` \| string \| no \| — \| Up to 500 chars. Concrete issues to avoid. \|
43	\| `enable_prompt_expansion` \| bool \| no \| true \| Auto-rewrites short prompts. Disable for literal control. \|
44	\| `seed` \| int \| no \| — \| 0..2^31-1. Reuse for variants. \|
45
46	## How to invoke
47
48	Default (5s 1080p 16:9, prompt-expanded):
49
50	```bash
51	runcomfy run wan-ai/wan-2-7/text-to-video \
52	--input '{"prompt": "<user prompt>"}' \
53	--output-dir <absolute/path>
54	```
55
56	Audio-driven lip-sync (your own track):
57
58	```bash
59	runcomfy run wan-ai/wan-2-7/text-to-video \
60	--input '{
61	"prompt": "Medium close-up of the spokesperson, warm key light, locked tripod, slight breathing motion.",
62	"audio_url": "https://.../voiceover.mp3",
63	"duration": 12,
64	"aspect_ratio": "9:16"
65	}' \
66	--output-dir <absolute/path>
67	```
68
69	Literal control (no auto-expansion):
70
71	```bash
72	runcomfy run wan-ai/wan-2-7/text-to-video \
73	--input '{
74	"prompt": "<exactly what you want, verbatim>",
75	"enable_prompt_expansion": false,
76	"negative_prompt": "no subtitles, no flicker, no distorted hands"
77	}' \
78	--output-dir <absolute/path>
79	```
80
81	## Prompting — what actually works
82
83	Camera + motion in plain English. "Slow dolly in", "locked tripod, low angle", "handheld follow", "crane move from above". Front-load the shot.
84
85	One primary action per clip. Don't pile up multiple competing actions. Pick the beat: "she turns, then smiles" not "she turns AND smiles AND a bus passes AND...".
86
87	Use `negative_prompt` for concrete issues. Good: "no subtitles, no watermark, no flicker". Bad (vague): "no bad lighting".
88
89	Prompt expansion is on by default. Short prompts get auto-rewritten by the model. For terse / literal prompts (e.g. brand-strict ad copy), disable with `enable_prompt_expansion: false`.
90
91	Audio specs matter. `audio_url` must be 3–30s, ≤15MB, WAV/MP3. Out-of-range files reject. Match audio length to clip duration.
92
93	Iterate seeds. Reuse the same seed when you want consistent output across variants of the same prompt. Change seed for genuine variety.
94
95	Anti-patterns:
96	- Static-frame descriptions → motion will be vague.
97	- Vague negatives ("no bad colors") → ignored.
98	- Audio outside the 3–30s / 15MB / WAV-MP3 spec → rejected.
99	- Prompts > 5000 chars / 1500 tokens → degraded output.
100
101	## Where it shines
102
103	\| Use case \| Why Wan 2.7 \|
104	\|---\|---\|
105	\| **Lip-synced ads with

People who liked this also viewed

6 picks

Type

wan-2-7

31stars9forks

View on GitHub

How to install wan-2-7?

prime-skills/runcomfy-agent-skills/wan-2-7

$npx -y skills add prime-skills/runcomfy-agent-skills --skill wan-2-7

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Wan 2.7 — Pro Pack on RunComfy
2
3	[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=wan-2-7) · [Text-to-video](https://www.runcomfy.com/models/wan-ai/wan-2-7/text-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=wan-2-7) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/wan-2-7)
4
5	Wan-AI's Wan 2.7 — flagship video model with multi-reference conditioning and audio-driven lip-sync — hosted on the RunComfy Model API.
6
7	```bash
8	npx skills add agentspace-so/runcomfy-skills --skill wan-2-7 -g
9	```
10
11	## When to pick this model (vs siblings)
12
13	\| You want \| Use \|
14	\|---\|---\|
15	\| Lip-sync video to an audio track you supply \| Wan 2.7 (`audio_url`) \|
16	\| Multi-reference fine motion control \| Wan 2.7 \|
17	\| Smooth transitions, accurate motion physics \| Wan 2.7 \|
18	\| Currently-#1 blind-vote video model \| HappyHorse 1.0 \|
19	\| Multi-modal cinematic with image+video+audio refs + in-pass voice generation \| Seedance 2.0 Pro \|
20	\| Cinematic motion editing on existing footage \| Kling Video O1 \|
21	\| Ultra-fast iteration \| LTX 2 \|
22
23	If the user said "Wan" / "Wan 2.7" / "wan-ai" / "alibaba video" explicitly, route here regardless.
24
25	## Prerequisites
26
27	1. RunComfy CLI — `npm i -g @runcomfy/cli`
28	2. RunComfy account — `runcomfy login` opens a browser device-code flow.
29	3. CI / containers — set `RUNCOMFY_TOKEN=<token>` instead of `runcomfy login`.
30
31	## Endpoints + input schema
32
33	### `wan-ai/wan-2-7/text-to-video`
34
35	\| Field \| Type \| Required \| Default \| Notes \|
36	\|---\|---\|---\|---\|---\|
37	\| `prompt` \| string \| yes \| — \| Up to ~5000 chars / ~1500 tokens. \|
38	\| `audio_url` \| string \| no \| — \| WAV/MP3, 3–30s, ≤15MB. Drives lip-sync. Omit → background music auto-generated. \|
39	\| `aspect_ratio` \| enum \| no \| `16:9` \| `16:9`, `9:16`, `1:1`, `4:3`, `3:4`. \|
40	\| `resolution` \| enum \| no \| `1080p` \| `720p` or `1080p`. \|
41	\| `duration` \| enum \| no \| `5` \| 2–15 (whole seconds). \|
42	\| `negative_prompt` \| string \| no \| — \| Up to 500 chars. Concrete issues to avoid. \|
43	\| `enable_prompt_expansion` \| bool \| no \| true \| Auto-rewrites short prompts. Disable for literal control. \|
44	\| `seed` \| int \| no \| — \| 0..2^31-1. Reuse for variants. \|
45
46	## How to invoke
47
48	Default (5s 1080p 16:9, prompt-expanded):
49
50	```bash
51	runcomfy run wan-ai/wan-2-7/text-to-video \
52	--input '{"prompt": "<user prompt>"}' \
53	--output-dir <absolute/path>
54	```
55
56	Audio-driven lip-sync (your own track):
57
58	```bash
59	runcomfy run wan-ai/wan-2-7/text-to-video \
60	--input '{
61	"prompt": "Medium close-up of the spokesperson, warm key light, locked tripod, slight breathing motion.",
62	"audio_url": "https://.../voiceover.mp3",
63	"duration": 12,
64	"aspect_ratio": "9:16"
65	}' \
66	--output-dir <absolute/path>
67	```
68
69	Literal control (no auto-expansion):
70
71	```bash
72	runcomfy run wan-ai/wan-2-7/text-to-video \
73	--input '{
74	"prompt": "<exactly what you want, verbatim>",
75	"enable_prompt_expansion": false,
76	"negative_prompt": "no subtitles, no flicker, no distorted hands"
77	}' \
78	--output-dir <absolute/path>
79	```
80
81	## Prompting — what actually works
82
83	Camera + motion in plain English. "Slow dolly in", "locked tripod, low angle", "handheld follow", "crane move from above". Front-load the shot.
84
85	One primary action per clip. Don't pile up multiple competing actions. Pick the beat: "she turns, then smiles" not "she turns AND smiles AND a bus passes AND...".
86
87	Use `negative_prompt` for concrete issues. Good: "no subtitles, no watermark, no flicker". Bad (vague): "no bad lighting".
88
89	Prompt expansion is on by default. Short prompts get auto-rewritten by the model. For terse / literal prompts (e.g. brand-strict ad copy), disable with `enable_prompt_expansion: false`.
90
91	Audio specs matter. `audio_url` must be 3–30s, ≤15MB, WAV/MP3. Out-of-range files reject. Match audio length to clip duration.
92
93	Iterate seeds. Reuse the same seed when you want consistent output across variants of the same prompt. Change seed for genuine variety.
94
95	Anti-patterns:
96	- Static-frame descriptions → motion will be vague.
97	- Vague negatives ("no bad colors") → ignored.
98	- Audio outside the 3–30s / 15MB / WAV-MP3 spec → rejected.
99	- Prompts > 5000 chars / 1500 tokens → degraded output.
100
101	## Where it shines
102
103	\| Use case \| Why Wan 2.7 \|
104	\|---\|---\|
105	\| **Lip-synced ads with

People who liked this also viewed

6 picks

Type